#3434th of 49 in Desktop AI appsFor finance and business, trading, stocks and crypto, finance and accounting
go-stock
Desktop stock analysis app with LLM agents for A-share, HK and US markets
- Stars
- 8.1k
- License
- GPL-3.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Go
5,273 on 21 Apr 20268,120 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
go-stock is a Wails and NaiveUI desktop app that combines A-share, Hong Kong and US market data with LLM-driven analysis. It includes K-line charting with technical indicators, an AI agent with 150+ data tools, MCP extensions, a knowledge base, prompt and recommendation backtesting, and Feishu/DingTalk push alerts. Models connect through OpenAI-compatible APIs, Ollama, LM Studio and Chinese providers. The UI and docs are in Chinese.
Who it is for: Chinese-speaking retail investors wanting LLM-assisted stock analysis
Strengths
- Agent modes React, PlanExecute and DeepAgents, with 150+ built-in market data tools and MCP support
- Works with local models (Ollama, LM Studio) and many OpenAI-compatible or Chinese cloud providers
- Backtests prompt templates and AI recommendations against historical data and the CSI 300 benchmark
- Pushes alerts to Feishu and DingTalk; signal monitor runs in the background
Weaknesses
- Developed mainly on Windows 10+; other platforms untested or have limited features
- README and UI are Chinese-only; market data is focused on China-centric sources
- Background signal monitor and market news sync require paid VIP2 sponsorship
- Project is stated as entertainment only; AI output is not investment advice
What it needs
- GPU optional
- Needs Edge browser for news scraping, LLM provider or local Ollama/LM Studio
- Models: OpenAI-compatible, Ollama, LM Studio, AnythingLLM, DeepSeek
Quick answers
Is go-stock open source?
Yes. Its code is on GitHub under the GPL-3.0 license.
Does go-stock need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Desktop AI apps
See all 49| Rank | Project | Score |
|---|---|---|
| 1 | cherry-studioDesktop client for chatting with many LLM providers, with agents and knowledge bases | 92 out of 100 |
| 2 | dsh-desktopNative Windows and macOS desktop client for DeepSeek Harness, built on plugins | 90 out of 100 |
| 3 | screenpipeRecords screen and audio locally, makes it searchable for you and your agents | 90 out of 100 |
| #4 | prompt-optimizerPrompt rewriting and testing tool for web, desktop, Chrome and MCP | 86 out of 100 |
| #5 | aionuiDesktop and WebUI app that runs a built-in agent plus external CLI agents | 86 out of 100 |